API Documentation

Integrate speech-to-speech AI into your applications with our simple REST API. SDKs available for Python, JavaScript, and more.

Quickstart Python SDK

Quickstart

Get started with the Speech to Speech AI API in under 5 minutes.

Base URL
https://api.speechtospeechai.com/v1
1. Install the SDK
Python 
pip install speechtospeechai
2. Generate Speech
Python 
from speechtospeechai import Client

client = Client(api_key="your-api-key")

# Generate speech from text
audio = client.audio.speech.create(
    model="kokoro",
    voice="af_heart",
    input="Hello! Welcome to Speech to Speech AI."
)

# Save to file
audio.save("output.mp3")
3. Clone a Voice
Python 
# Clone a voice from an audio sample
voice = client.voices.clone(
    name="My Custom Voice",
    files=["sample.mp3"]
)

# Use the cloned voice
audio = client.audio.speech.create(
    model="chatterbox",
    voice=voice.id,
    input="This is my cloned voice speaking!"
)

audio.save("cloned_output.mp3")

Authentication

All API requests require authentication via an API key in the Authorization header.

Header 
Authorization: Bearer YOUR_API_KEY
Get your API key from your account dashboard.

Voice Cloning

POST /v1/voices/clone

Clone a voice from an audio sample.

Request Body (multipart/form-data)
Parameter Type Required Description
name string Yes Name for the cloned voice
file file Yes Audio file (10-30 seconds recommended)
model string No Model to use (default: chatterbox)
language string No Language code (auto-detected if not specified)
Response
{
  "id": "voice_abc123xyz",
  "name": "My Custom Voice",
  "model": "chatterbox",
  "language": "en",
  "status": "ready",
  "created_at": "2026-02-03T12:00:00Z"
}

Text to Speech

POST /v1/audio/speech

Convert text to speech audio.

Request Body (JSON)
{
  "model": "kokoro",
  "voice": "af_heart",
  "input": "Hello, world!",
  "speed": 1.0,
  "format": "mp3",
  "emotion": "neutral"
}
Parameter Type Required Description
model string Yes TTS model (kokoro, orpheus, openvoice, etc.)
voice string Yes Voice ID (preset or cloned)
input string Yes Text to convert (max 5000 chars)
speed float No Speed multiplier (0.5-2.0, default 1.0)
format string No Output format (mp3, wav, ogg, flac)
emotion string No Emotion tag (neutral, happy, sad, angry)
Response

Returns audio file binary with appropriate Content-Type header.

Speech to Text

POST /v1/audio/transcriptions

Transcribe audio to text with timestamps.

Request Body (multipart/form-data)
Parameter Type Required Description
file file Yes Audio/video file to transcribe
model string No Model (whisper-large-v3, whisper-turbo)
language string No Language code (auto-detected if not set)
timestamps string No Timestamp granularity (word, segment)
Response
{
  "text": "Hello, how are you today?",
  "language": "en",
  "duration": 3.5,
  "segments": [
    {
      "start": 0.0,
      "end": 1.2,
      "text": "Hello,"
    },
    {
      "start": 1.3,
      "end": 3.5,
      "text": "how are you today?"
    }
  ]
}

Available Models

Text-to-Speech Models
Model ID Description Best For
kokoro Fast multilingual TTS General use, low latency
orpheus Expressive Llama-based TTS Emotional content, streaming
openvoice Fast voice cloning and conversion Quick turnaround, voice conversion
chatterbox Zero-shot voice cloning, 23 languages Cloning from a short sample
Speech-to-Text Models
Model ID Description Best For
whisper-large-v3 OpenAI Whisper Large v3 Highest accuracy, multilingual
whisper-turbo Optimized Whisper for speed Fast transcription
canary-qwen-2.5b NVIDIA Canary Qwen Lowest WER, English focus

Error Codes

Code Status Description
invalid_api_key 401 Invalid or missing API key
insufficient_credits 402 Not enough credits for this operation
rate_limit_exceeded 429 Too many requests
invalid_request 400 Malformed request body
model_not_found 404 Requested model doesn't exist
voice_not_found 404 Requested voice doesn't exist
file_too_large 413 Uploaded file exceeds size limit
server_error 500 Internal server error